Which is cheaper, Gemini 2.5 Flash Lite (batch) or UI-TARS 7B ?

Gemini 2.5 Flash Lite (batch) is the cheaper of the two: one 1,000-word request costs about 94 toman, about 1.2× cheaper than UI-TARS 7B .

Which one has the larger context window?

Gemini 2.5 Flash Lite (batch), with 1,048,576 tokens.

Gemini 2.5 Flash Lite (batch) vs UI-TARS 7B

Both sit behind the same key and the same code on uttapen — the only thing that changes is the model string, so you can run each of them against your own workload without touching anything else. On cost, Gemini 2.5 Flash Lite (batch) comes out about 1.2× cheaper.

Feature	Gemini 2.5 Flash Lite (batch)	UI-TARS 7B
Provider	Google	ByteDance
Model id	google/gemini-2.5-flash-lite:batch	bytedance/ui-tars-1.5-7b
Context	1,048,576 tokens	128,000 tokens
Max output	65,535 tokens	2,048 tokens
Input / 1M tokens	14,506 toman	29,013 toman
Output / 1M tokens	58,025 toman	58,025 toman
≈ one 1,000-word request	94 toman	113 toman
Input caching	2,901 toman / 1M	29,013 toman / 1M
Image input	Yes	Yes
File input	Yes	No
Tool calling	Yes	No
JSON output	Yes	Yes
Reasoning mode	Yes	No

Which one for what?

Gemini 2.5 Flash Lite (batch)

Multi-step problems, maths, and tracking down a bug
Whole documents or a codebase in a single request
Reading screenshots, invoices, and scanned forms
Agents that call your own APIs and database
High-volume work where cost per call decides

94 toman per 1,000 words · Model page

UI-TARS 7B

Reading screenshots, invoices, and scanned forms
High-volume work where cost per call decides

113 toman per 1,000 words · Model page

Run both with the same code

Swap the model value between the two ids and send the same request twice; what each answer cost comes back in the X-Uttapen-Cost-Toman header.

curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash-lite:batch",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence."}],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uttapen.ir/v1",
    api_key="sk-up-…",
)

stream = client.chat.completions.create(
    model="google/gemini-2.5-flash-lite:batch",
    messages=[{"role": "user", "content": "Introduce yourself in one sentence."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.uttapen.ir/v1",
  apiKey: "sk-up-…",
});

const stream = await client.chat.completions.create({
  model: "google/gemini-2.5-flash-lite:batch",
  messages: [{ role: "user", content: "Introduce yourself in one sentence." }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

<?php
// composer require openai-php/client guzzlehttp/guzzle
$client = OpenAI::factory()
    ->withBaseUri('https://api.uttapen.ir/v1')
    ->withApiKey('sk-up-…')
    ->make();

$result = $client->chat()->create([
    'model' => 'google/gemini-2.5-flash-lite:batch',
    'messages' => [['role' => 'user', 'content' => 'Introduce yourself in one sentence.']],
]);
echo $result->choices[0]->message->content;

package main

import (
	"context"
	"fmt"

	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	client := openai.NewClient(
		option.WithBaseURL("https://api.uttapen.ir/v1"),
		option.WithAPIKey("sk-up-…"),
	)
	resp, err := client.Chat.Completions.New(context.Background(), openai.ChatCompletionNewParams{
		Model:    "google/gemini-2.5-flash-lite:batch",
		Messages: []openai.ChatCompletionMessageParamUnion{openai.UserMessage("Introduce yourself in one sentence.")},
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(resp.Choices[0].Message.Content)
}

model = "bytedance/ui-tars-1.5-7b"

More comparisons: all pairs · model rankings · full catalogue

base_url = https://api.uttapen.ir/v1